Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly/idempotent/non-destructive annotations, the description fully discloses the behavioral contract: it returns {answer, evidence, confidence, source, fetched_at, refusal_reason} on success, and an explicit refusal object with enumerated refusal_reason values. It also reveals that the answer is extracted exclusively from the tool result, which is central behavioral context not inferable from annotations. No contradiction with the annotations exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense and front-loaded, opening with the core purpose and routing before moving to output shape and usage guidance. Most sentences earn their place, but the core safety idea is repeated three times ('Hallucination-resistant', 'using ONLY what the tool result contains', 'must not invent facts'), which keeps it from a perfect 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the full burden of explaining return values and failure modes, and it does so thoroughly, including the exact refusal_reason enum. It covers success shape, evidence extraction, cost implications, and when to prefer the cheaper sibling. The definition is complete for an agent to invoke and interpret the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already documents 'question' and 'output_format' with aliases and priority, and schema description coverage is 100%. The tool description does not add new meaning to the parameters themselves beyond what the schema provides. Baseline 3 is appropriate because the schema carries the semantic weight.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Hallucination-resistant answer mode for high-stakes reads' that 'EXTRACTS the answer using ONLY what the tool result contains.' It explicitly ties itself to 'Same routing as ask_pipeworx' and distinguishes itself from sibling ask_pipeworx by the grounded extraction behavior. An agent can immediately tell this is the cited-evidence answer mode rather than the general ask_pipeworx tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit when-to-use guidance: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts,' with concrete domains including financial, legal, medical, and public statements. It also gives a when-not-to-use with an alternative: 'prefer ask_pipeworx for casual lookups' and explains the tradeoff of one extra LLM call. This is actionable routing information.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.